Agent skill · security · bighardperson
skill-scanner
Scan installed OpenClaw skills for malicious code patterns including ClickFix social engineering, reverse shell (RAT), and data exfiltration. Uses OG-Text model for agentic detection.
Why this skill is useful
Adds a comprehensive scanning script that detects malicious patterns in OpenClaw skills, which the AI cannot generate on its own.
What it needs
Requires curl installed locally. About 7k tokens when loaded. Last updated 2026-04-26. 34 stars on the source repository.
What this skill does
Skill Scanner — Malicious Skill Detection for OpenClaw Scan all installed OpenClaw skills to detect hidden malicious behavior such as: ClickFix — Social engineering that tricks users into downloading and running malicious code (e.g., fake update prompts, disguised install commands) RAT (Remote Access Trojan) — Reverse shells, backdoors, or covert command-and-control connections Info Stealer — Exfiltration of credentials, SSH keys, tokens, environment variables, browser data, or keychain items How It Works This skill uses the OG-Text security model to analyze each installed skill's source code. The agent reads skill files, chunks long content, sends each chunk to the model with a specialized security prompt, and aggregates the findings into a risk report. Workflow Follow these steps in order when the user asks to scan skills. Step 1: Discover installed skills Find all installed skill directories. Skills can be in multiple locations: For each directory found, look for these files that define a skill: SKILL.md — Skill definition and instructions .ts, .js — Source code (TypeScript/JavaScript) .sh, .bash — Shell scripts .py — Python scripts package.json — Package definition with dependencies openclaw.plugin.json — Plugin configuration Step 2: Read and collect skill content For each skill found, read ALL source files. Prioritize files in this order: 1. Any .ts, .js, .sh, .bash, .py files (executable code — highest risk) 2. SKILL.md (may contain embedded shell commands or curl calls) 3. package.json (check for suspicious dependencies or scripts) 4. openclaw.plugin.json (check for dangerous hooks or permissions) Concatenate all content for each skill with clear file markers: Step 3: Chunk the content If a skill's combined content exceeds 4000 characters, split it into chunks: Chunk size: 4000 characters Overlap: 200 characters (to catch malicious patterns that span chunk boundaries) If the content is under 4000 characters, treat it as a single chunk. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills bighardperson/antivirus